Learning

In learning, I have used different forms of machine learning to innovate for business application.

I am currently working on detecting and handling of adversarial attacks on AI services from training data and rating AI services for bias (AIES 2018). Other recent work are on recommendation strategies for information elicitation (IUI 2018) and characterizing and predicting delays of trains in India using zero-shot learning (IEEE ITSC 2018). I had previously worked on understanding social network spread (UAI 2013), product recommendation (EC-Web 2002), and automatic tuning of parameters for planners (AAAI 2005).

Papers

    1. Ramashish Gaurav, Biplav Srivastava, Estimating Train Delays in a Large Rail Network Using a Zero Shot Markov Model, IEEE International Conference on Intelligent Transportation Systems (ITSC). On Arxiv at: https://arxiv.org/abs/1806.02825, April 2018 [Area: Train delay, learning]

    2. Biplav Srivastava, Francesca Rossi, Towards Composable Bias Rating of AI Systems, 2018 AI Ethics and Society Conference (AIES 2018), New Orleans, Lousiana, USA, Feb 2-3, 2018. [Area: AI Service Rating, Ethics]

    3. Yunfeng Zhang, Vera Liao, Biplav Srivastava, Towards an optimal dialog strategy for information retrieval using both open-ended and close-ended questions, Proc. Intelligent User Interfaces (IUI 2018, Tokyo, Japan, March 2018 [Area: Dialog Strategy].

    4. Akshat Kumar, Dan Sheldon, Biplav Srivastava, Collective Diffusion Over Networks: Models and Inference, Uncertainty in Artificial Intelligence (UAI 2013), 2013. [Area: Machine Learning-Social Network]

    5. B. Srivastava, A. Mediratta, Domain-Dependent Parameter Selection of Search-based Algorithms Compatible with User Performance Criteria , Proceedings of the 25th National Conference on Artificial Intelligence (AAAI-05), Pittsburgh, USA. [Area: parameter selection, learning]

    6. N. Modani, P. Mittal, A. Nanavati, B. Srivastava, Series of Dynamic Targeted Recommendations, In Proc. EC-Web, Aix-en-Provence, France, 2002. [Area: E-commerce, online learning]

Patents and applications

    1. US 7,617,122 - Targeted online marketing [tags: decision support]

    2. 20080300934, 20080300929 - System and method for evolutionary learning of best-of-breed business processes